An Illinois Tech professor who developed an artificial pancreas for diabetics has been awarded $1.2 million by the National Institutes of Health to continue developing the device.
A typical person with type 1 diabetes must decide between 100 and 200 times each day whether they need to eat, drink, inject insulin, etc.
“Part of the function of their pancreas is turned over to their brain,”
Cinar, who is also the Hyosung S. R. Cho Endowed Chair in Engineering
Effects of Not Getting Proper Insulin Dose
If they don’t give themselves enough time to eat before exercise, they might feel weak, dizzy, faint, or even worse if their blood sugar becomes too low.
If your blood sugar level is often out of the target range or if it’s too high, you may develop serious health conditions including heart disease, diabetes, and even blindness.
Current Automated Insulin Delivery Systems
Most current automated diabetes management systems require that the patient manually enter carbohydrate values into the device.
They also expect that users will manually adjust their workouts if they’re not working out correctly. This requires time and effort and leaves this important medical task open to human error.
Limitations
People who are particularly vulnerable to not entering their calorie information include young adults, elderly people, and people who suffer from memory loss.
Current blood sugar monitors don’t account for everything that affects blood sugar levels. Stress, sleep, and other things besides food and physical activity can either raise or lower blood sugar levels.
Read more trending news.
Cinar
Cinar has been at the forefront of this technology for many decades.
Incorporate Data through Wearable Systems
He was the first to incorporate sensor data from wearable devices such as a sports watch into the control system of an artificial pancreas.
Decision-Making Algorithm
This new technology analyzes a person’s history more thoroughly than ever before by using machine learning and customizes the system’s decisions to better predict whether someone is likely to engage in behaviors that could affect their blood sugar level.
Predictive ability is important because there’s a time lag between when insulin is given and when it starts working.
“If someone eats lunch at noon every day and the meal has usually 20 to 30 grams of carbohydrates, then if their current blood glucose level is not very low, at 11:45 we could say, ‘Everything indicates that the trend of this day is a typical weekday for this person, so let’s give them, not the whole dose of insulin, but a little bit of it so that it will blunt the meal effect on the glucose,’” says Cinar.
Collaboration
Machine learning and artificial intelligent algorithm developed by Associate Professor of Computer Science at UC Irvine, Mustafa Bilgic, will be able to predict the future actions of an individual based on their past behaviors.
You can find more information on our website.
How It Works?
A computer program would calculate the probability that the person will eat lunch soon by analyzing their behavior on the current date and then administering an appropriate insulin dosage.
If the blood sugar levels start rising, then it would administer extra insulin.
Artificial Pancreas
An artificial pancreas designed to automatically adjust its output according to the user’s needs would be able to take into account the presence of these factors when determining the appropriate dosage.
A system that assumes that someone is physically active when their heart rate is elevated could be wrong if they’re stressed out.
Glucose Level
However, stress and physical activity both affect glucose levels in opposite ways, so the system may increase your blood sugar by reducing your body’s production of the hormone responsible for lowering blood sugar (insulin).
Multiple factors can affect one another at once. For example, if a person runs for an hour, their blood sugar levels may rise due to both physical activity and eating something before running.
“That’s why we really changed our focus from just detecting exercise to detecting the state of the person,”
Cinar
“And it’s becoming more and more interesting and challenging.”
With enough historical data from people who seem to be behaving irrationally, the machine learning system could learn to identify when someone seems to be acting irrationally.
“The advantage of powerful machine learning tools is to be able to tease out the secondary relations that exist. No matter how erratic people claim that their behavior is, there are always certain patterns that can be captured,”
Cinar
“It could be five patterns for someone who is very routine-based and 15 patterns for someone less routine-based. The system can look at how the day is developing on and then look at the dictionary of patterns to say, ‘Oh, this is similar to pattern number 17, so let’s assume that the rest of the day will go accordingly.’”
Cinar aims to provide people with type 1 or 2 diabetes the ability to live their life without having to constantly evaluate whether they need to log what foods they eat into their insulin pump.
“Someone may be running to catch the bus because the bus is coming too soon or they were late leaving their home. That’s not something that they want to stop midway to adjust the insulin dosing. So that’s why we would like to make a fully automated system,”
Cinar
Conclusion
The goal of this research project is to create a system that can detect the state of the user and determine the best way to manage their blood sugar levels.
Currently, most people have to manually enter their carbohydrate intake into their insulin pumps.
This process is prone to errors and takes up valuable time.
